3 papers
stat.ML2026
Learning to Recall with Transformers Beyond Orthogonal Embeddings
Nuri Mert Vural, Alberto Bietti, Mahdi Soltanolkotabi +1
Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this ca…
stat.ML2025
Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
Gérard Ben Arous, Murat A. Erdogdu, Nuri Mert Vural +1
We study the optimization and sample complexity of gradient-based training of a two-layer neural network with quadratic activation function in the high-dimensional regime, where th…
stat.ML2024
Pruning is Optimal for Learning Sparse Features in High-Dimensions
Nuri Mert Vural, Murat A. Erdogdu
While it is commonly observed in practice that pruning networks to a certain level of sparsity can improve the quality of the features, a theoretical explanation of this phenomenon…